Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Released Expert-as-a-Service (EaaS) for MoE serving, Sep 22, 2025
- One paper accepted by NeurIPS '25, Sep 18, 2025
- Awarded the “Stars of Tomorrow” Certificate from MSRA (top 10% intern), Dec 9, 2024
- Released RAS for efficient DiTs, Dec 9, 2024
- One paper accepted by PPoPP 2025, Nov 12, 2024
- One paper accepted by ASPLOS '25, Oct 3, 2024
- Awarded the SoC Teaching Fellowship (3 out of all NUS CS PhD), Jun 27, 2024
- One paper accepted by MLSYS 2024, Feb 16, 2024
- One paper accepted by ICLR '24, Jan 15, 2024
- One paper accepted by SC '23, Jun 17, 2023
Research Experience
- Research Intern, Qiji Zhifeng, January 2025 – Present, working on large-scale MoE model serving system
- Research Intern, Microsoft Research, May 2024 – November 2024, working on sparse inference and training of text-to-image and text-to-video models, supervised by Dr. Zhenhua Han and Dr. Yuqing Yang
- Research Intern, HPC-AI Tech, May 2022 – December 2022, responsibilities include developing the efficient LLM inference system EnergonAI and optimizing the implementation of ColossalAI
- Machine Learning Engineer, ByteDance, September 2020 – June 2021, NLP algorithm engineer at Lark, ByteDance
Education
- PhD in Computer Science, National University of Singapore, January 2023 – Present, Advisor: Prof. Yang You
- MSc in Artificial Intelligence, National University of Singapore, August 2021 – January 2023
- BSc in Computer Science, Peking University, September 2016 – July 2020, Advisor: Prof. Tong Yang
Background
Research Interests: Machine Learning Systems, High Performance Computing, Distributed Training & Inference, Sparse Inference & Training. About Me: Currently a third-year CS Ph.D. candidate at NUS, supervised by Prof. Yang You. Previously an intern at Microsoft Research, supervised by Dr. Zhenhua Han and Dr. Yuqing Yang.
Miscellany
Looking forward to collaborations and research internship opportunities